LLM Benchmarks — Scores, Methodology & Live Rankings

What each benchmark measures, how models score, and the current rankings

Most tested benchmarks

Ranked by how many models have tracked scores — open a benchmark for its full live ranking.

HumanEval+ 3 models tested · latest result 03.10.2026 95.12% HumanEval 3 models tested · latest result 27.02.2025 48.8% MBPP 3 models tested · latest result 27.02.2025 65.6% MBPP+ 2 models tested · latest result 17.09.2026 83.07% CRUXEval 2 models tested 86.7%

MBPP

Code

Mostly Basic Python Problems - Python coding tasks. 3-shot.

Active View →

HumanEval

Code

HumanEval - Python code generation from function signatures and docstrings. 0-shot.

Active View →

CRUXEval

Code

CRUXEval: code reasoning (output prediction and input execution over short Python snippets), scored as accuracy on a 0-100 scale in Cloudflare's internal Dec...

Active View →

HumanEval+

Code

HumanEval+ is the EvalPlus extension of HumanEval with 80x more generated unit tests for correctness checking. Score recorded from the Bonsai 2 27B GGUF card...

Active View →

MBPP+

Code

MBPP+ is the EvalPlus extension of Mostly Basic Python Problems with hardened test suites. Score recorded from the Bonsai 2 27B GGUF card's Full Per-Benchmar...

Active View →